End-to-end multiple object tracking in high-resolution optical sensors of drones with transformer models by Yubin Yuan, Yiquan Wu, Langyue Zhao, Yuqi Liu, Yaxuan Pang

Get full text

Machine learning-based coronary heart disease diagnosis model for type 2 diabetes patients by Yingxi Chen, Chunyu Wang, Chunyu Wang, Xiaozhu Liu, Minjie Duan, Tianyu Xiang, Haodong Huang, Haodong Huang

“…Among all models, the XgBoost model based on features selected by RFE+LightGBM demonstrated the best performance, achieving an AUC of 0.814 (95% CI, 0.779-0.847), accuracy of 0.799 (95% CI, 0.771-0.827), precision of 0.841 (95% CI, 0.812-0.868), recall of 0.920 (95% CI, 0.898-0.941), and F1-score of 0.879 (95% CI, 0.859-0.897) in the testing set.ConclusionsBased on T2DM data and machine learning theory, a Bayesian-optimized XgBoost model was established using the RFE+LightGBM method. …”
Get full text

Machine learning models for predicting in-hospital mortality from acute pancreatitis in intensive care unit by Shuxing Wei, Hongmeng Dong, Weidong Yao, Ying Chen, Xiya Wang, Wenqing ji, Yongsheng Zhang, Shubin Guo

“…To enhance interpretability and identify key predictive features, we implemented Shapley Additive Explanations (SHAP) analysis for the top-performing model. …”
Get full text

STIED: a deep learning model for the spatiotemporal detection of focal interictal epileptiform discharges with MEG by Raquel Fernández-Martín, Alfonso Gijón, Odile Feys, Elodie Juvené, Alec Aeby, Charline Urbain, Xavier De Tiège, Vincent Wens

“…Our DL model enabled a successful identification of IEDs in patients suffering from focal epilepsy with frequent and high amplitude spikes (FE group), with high-performance metrics—accuracy, specificity, and sensitivity all exceeding 85%—when learning from spatiotemporal features of IEDs. …”
Get full text

Intelligent Detection of Oceanic Front in Offshore China Using EEFD-Net with Remote Sensing Data by Ruijie Kong, Ze Liu, Yifei Wu, Yong Fang, Yuan Kong

“…In view of the weak edge nature of oceanic fronts and the misdetection or missed detection of oceanic fronts by some deep learning methods, this paper proposes an oceanic front detection method based on the U-Net model that integrates Edge-Attention-Module and the Feature Pyramid Network Module (FPN-Module). …”
Get full text

PRIVACY-AWARE MALARIA DETECTION: U-NET MODEL WITH K-ANONYMITY FOR CONFIDENTIAL IMAGE ANALYSIS by Ghazala Hcini, Imen Jdey

“…The model features a custom Spatial Attention mechanism for improved segmentation performance and incorporates advanced techniques to focus on critical image features. …”
Get full text

MCIR-YOLO: White Medication Pill Classification Using Multi-Band Infrared Images by Mohan Wang, Yang Jiang, Baohui Xu, Mengqiang Huang, Xu Xue, Xu Wu, Wenjian Kuang, Xiang Liu, Harm Tolner

“…Notably, the utilization of the MCIR-YOLO model for six-channel recognition yields a substantial advantage of 12.05% over the best-performing single-channel IR image recognition.…”
Get full text

Development and validation of a clinical prediction model for osteoporosis diagnosis by lumbosacral X-ray and radiomics by Xiaofeng Chen, Xiaofeng Chen, Dongling Cai, Dongling Cai, Hao Li, Weijun Guo, Qian Li, Qian Li, Jinjun Liang, Junxian Xie, Jincheng Liu, Zhen Xiang, Wenxuan Dong, Sihong OuYang, Zhuozheng Deng, Qipeng Wei

“…Performance evaluations for various models were conducted, encompassing recognition ability, accuracy, and clinical value, with the aim of identifying and optimizing prediction models.ResultsThe 12 most optimal imaging features were identified. …”
Get full text

A Multifeature Fusion Short-Term Traffic Flow Prediction Model Based on Deep Learnings by Chunxu Chai, Chuanxiang Ren, Changchang Yin, Hui Xu, Qiu Meng, Juan Teng, Ge Gao

“…Moreover, a feature fusion layer in the model is used to fuse the features extracted by each module. …”
Get full text

Sentiment analysis for deepfake X posts using novel transfer learning based word embedding and hybrid LGR approach by Madiha Khalid, Muhammad Faheem Mushtaq, Urooj Akram, Mejdl Safran, Sultan Alfarhood, Imran Ashraf

“…The ML models are fine-tuned with extensive hyperparameter tuning to enhance performance and efficiency. …”
Get full text

Machine learning-based risk prediction model for pertussis in children: a multicenter retrospective study by Juan Xie, Run-wei Ma, Yu-jing Feng, Yuan Qiao, Hong-yan Zhu, Xing-ping Tao, Wen-juan Chen, Cong-yun Liu, Tan Li, Kai Liu, Li-ming Cheng

“…Methods First, data from 1085 suspected pertussis patients from 7 centers were collected, and ten key features were analyzed using the lasso regression and Boruta algorithm: PDW-MPV-RATIO, SII, white blood cells, platelet distribution width, mean platelet volume, lymphocytes, cough duration, vaccination, fever, and lytic lymphocytes.Eight models were then trained and validated to assess their performance and to confirm their generalization ability with external datasets based on these features. …”
Get full text

Effect of Noises and GSM Codings on Pre-Trained Speaker Embedding Models in Forensic Voice Comparison by Mohammed Hamzah Alsalihi, David Sztaho

“…Results show that environmental noise and GSM coding significantly degrade speaker verification performance. The best-performing model, ECAPA-TDNN, achieved a minimum EER of 1% and a <inline-formula> <tex-math notation="LaTeX">${C} _{\text {llr}}$ </tex-math></inline-formula> of 0.048 in clean conditions with speaker enrollment. …”
Get full text

Superiority of Classification Tree versus Cluster, Fuzzy and Discriminant Models in a Heartbeat Classification System. by Vessela Krasteva, Irena Jekova, Remo Leber, Ramun Schmid, Roger Abächerli

“…The training with European ST-T, AHA, MIT-BIH Supraventricular Arrhythmia databases found the best performance settings of all classification models: Cluster (30 features), Fuzzy (72 features), LDA (142 coefficients), CT (221 decision nodes) with top-3 best scored features: normalized current RR-interval, higher/lower frequency content ratio, beat-to-template correlation. …”
Get full text

Measuring Raven’s Progressive Matrices Combining Eye-Tracking Technology and Machine Learning (ML) Models by Shumeng Ma, Ning Jia

“…Using eye-tracking metrics as features, ten ML models were trained, with the XGBoost model demonstrating superior performance. …”
Get full text

Habitat radiomics and transformer fusion model to evaluate treatment effectiveness of cavitary MDR-TB patients by Xinna Lv, Yichuan Wang, Chenyu Ding, Lixin Qin, Xiaoyue Xu, Ye Li, Dailun Hou

“…Then, a transformer-based fusion model integrating features from all regions was established. …”
Get full text

MATHEMATICAL MODEL OF THE LOAD BALANCING SYSTEM OF DPC SERVER CLUSTERS UNDER FRACTAL LOAD CONDITIONS by V. P. Mochalov, N. Yu. Bratchenko, I. S. Palkanov, E. V. Aliev

“…The performance of the proposed model and the verification of the results obtained were carried out by simulation. …”
Get full text

Renewable energy forecasting using optimized quantum temporal model based on Ninja optimization algorithm by Mona Ahmed Yassen, El-Sayed M. El-kenawy, Mohamed Gamal Abdel-Fattah, Islam Ismael, Hossam El.Deen Salah Mostafa

“…The research utilizes QTM with NiOA optimization for achieving maximum forecasting performance. NiOA functions through critical optimization processes when enhancing deep learning models with high accuracy for large complex datasets by selecting the most appropriate features. …”
Get full text

TrapMI: A Data Protection Method to Resist Model Inversion Attacks in Split Learning by Hyunsik Na, Daeseon Choi

“…However, concerns remain regarding data privacy leakage because an attacker can still attempt model inversion attacks based on the intermediate features. …”
Get full text

A Hybrid Artificial Intelligence Approach for Down Syndrome Risk Prediction in First Trimester Screening by Emre Yalçın, Serpil Aslan, Mesut Toğaçar, Süleyman Cansun Demir

“…The proposed method transforms one-dimensional (1D) patient data—including features such as nuchal translucency (NT), human chorionic gonadotropin (hCG), and pregnancy-associated plasma protein A (PAPP-A)—into two-dimensional (2D) Aztec barcode images, enabling advanced feature extraction using transformer-based deep learning models. …”
Get full text

Detection and Localization of Stationary Waves on Venus Using a Self‐Supervised Anomaly Detection Model by Husnu Baris Baydargil, Jose Eduardo Oliveira Silva, Yeon Joo Lee, Meeyoung Cha

“…Our model is developed over Akatsuki images of Venus and is trained on smaller cropped images containing features other than stationary waves, allowing it to learn the underlying patterns of normal cloud features. …”
Get full text